LSTM-ED for Anomaly Detection in Time Series Data¶
In [ ]:
import time
import numpy as np
import pandas as pd
import matplotlib.pyplot as plt
import tensorflow as tf
from dataset import *
from plots import *
from metrics import *
from models_funtions import *
# Set style for matplotlib
plt.style.use("Solarize_Light2")
import plotly.io as pio
pio.renderers.default = "notebook_connected"
In [ ]:
# Path to the root directory of the dataset
ROOTDIR_DATASET_NORMAL = '../dataset/normal'
ROOTDIR_DATASET_ANOMALY = '../dataset/collisions'
# TF_ENABLE_ONEDNN_OPTS=0 means that the model will not use the oneDNN library for optimization
import os
os.environ['TF_ENABLE_ONEDNN_OPTS'] = '0'
Variours parameters¶
In [ ]:
#freq = '1.0'
#freq = '0.1'
freq = '0.01'
#freq = '0.005'
file_name_normal = "_20220811_rbtc_"
file_name_collisions = "_collision_20220811_rbtc_"
recording_normal = [0, 2, 3, 4]
recording_collisions = [1, 5]
freq_str = freq.replace(".", "_")
features_folder_normal = f"./features/normal{freq_str}/"
features_folder_collisions = f"./features/collisions{freq_str}/"
Data¶
In [ ]:
df_features_normal, df_normal_raw, _ = get_dataframes(ROOTDIR_DATASET_NORMAL, file_name_normal, recording_normal, freq, f"{features_folder_normal}")
df_features_collisions, df_collisions_raw, df_collisions_raw_action = get_dataframes(ROOTDIR_DATASET_ANOMALY, file_name_collisions, recording_collisions, freq, f"{features_folder_collisions}1_5/")
df_features_collisions_1, df_collisions_raw_1, df_collisions_raw_action_1 = get_dataframes(ROOTDIR_DATASET_ANOMALY, file_name_collisions, [1], freq, f"{features_folder_collisions}1/")
df_features_collisions_5, df_collisions_raw_5, df_collisions_raw_action_5 = get_dataframes(ROOTDIR_DATASET_ANOMALY, file_name_collisions, [5], freq, f"{features_folder_collisions}5/")
Loading data. Found 31 different actions. Loading data done. Loading features from file. --- 0.023478269577026367 seconds --- Loading data. Found 31 different actions. Loading data done. Loading features from file. --- 0.019075393676757812 seconds --- Loading data. Found 31 different actions. Loading data done. Loading features from file. --- 0.013525724411010742 seconds --- Loading data. Found 31 different actions. Loading data done. Loading features from file. --- 0.013577461242675781 seconds ---
In [ ]:
X_train, y_train, X_test, y_test, df_test = get_train_test_data(df_features_normal, df_features_collisions, full_normal=True)
X_train_1, y_train_1, X_test_1, y_test_1, df_test_1 = get_train_test_data(df_features_normal, df_features_collisions_1, full_normal=True)
X_train_5, y_train_5, X_test_5, y_test_5, df_test_5 = get_train_test_data(df_features_normal, df_features_collisions_5, full_normal=True)
c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\.venv\Lib\site-packages\sklearn\base.py:493: UserWarning: X does not have valid feature names, but VarianceThreshold was fitted with feature names c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\.venv\Lib\site-packages\sklearn\base.py:493: UserWarning: X does not have valid feature names, but VarianceThreshold was fitted with feature names c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\.venv\Lib\site-packages\sklearn\base.py:493: UserWarning: X does not have valid feature names, but VarianceThreshold was fitted with feature names
Collisions¶
In [ ]:
collisions_rec1, collisions_init1 = get_collisions('1', ROOTDIR_DATASET_ANOMALY)
collisions_rec5, collisions_init5 = get_collisions('5', ROOTDIR_DATASET_ANOMALY)
# Merge the collisions of the two recordings in one dataframe
collisions_rec = pd.concat([collisions_rec1, collisions_rec5])
collisions_init = pd.concat([collisions_init1, collisions_init5])
In [ ]:
collisions_zones, y_collisions = get_collisions_zones_and_labels(collisions_rec, collisions_init, df_features_collisions)
collisions_zones_1, y_collisions_1 = get_collisions_zones_and_labels(collisions_rec1, collisions_init1, df_features_collisions_1)
collisions_zones_5, y_collisions_5 = get_collisions_zones_and_labels(collisions_rec5, collisions_init5, df_features_collisions_5)
RNN-EBM for Anomaly Detection in Time Series Data¶
In [ ]:
from algorithms.rnn_ebm import RecurrentEBM
# Disable eager execution
tf.compat.v1.disable_eager_execution()
classifier = RecurrentEBM(
num_epochs=100,
n_hidden=64,
n_hidden_recurrent=32,
min_lr=1e-4,
min_energy=None, # We'll set this to None initially and determine it after training
batch_size=128,
seed=42,
gpu=None # Set to None for CPU, or specify GPU index if available
)
# Train the RNN on normal data
classifier.fit(X_train)
print("RNN-EBM training completed.")
100%|██████████| 100/100 [00:14<00:00, 7.12it/s]
RNN-EBM training completed.
Predictions¶
In [ ]:
df_test = get_statistics(X_test, y_collisions, classifier, df_test, freq, threshold_type="mad")
df_test_1 = get_statistics(X_test_1, y_collisions_1, classifier, df_test_1, freq, threshold_type="mad")
df_test_5 = get_statistics(X_test_5, y_collisions_5, classifier, df_test_5, freq, threshold_type="mad")
Anomaly prediction completed.
Number of anomalies detected: 3 with threshold 24630.804321289062, std
Number of anomalies detected: 109 with threshold 135.32739639282227, mad
Number of anomalies detected: 16 with threshold 548.552001953125, percentile
Number of anomalies detected: 18 with threshold 507.74287700653076, IQR
Number of anomalies detected: 306 with threshold 0.0, zero
choosen threshold type: mad, with value: 135.3274
F1 Score: 0.8692
Accuracy: 0.9085
Precision: 0.8532
Recall: 0.8857
precision recall f1-score support
0 0.94 0.92 0.93 201
1 0.85 0.89 0.87 105
accuracy 0.91 306
macro avg 0.90 0.90 0.90 306
weighted avg 0.91 0.91 0.91 306
ROC AUC Score: 0.9250
c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\.venv\Lib\site-packages\numpy\lib\type_check.py:518: RuntimeWarning: overflow encountered in cast c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\.venv\Lib\site-packages\numpy\lib\type_check.py:519: RuntimeWarning: overflow encountered in cast
Anomalies detected: 109
Best threshold: 113.2632 | F1 Score: 0.8947 | Precision: 0.8293 | Recall: 0.9714
Anomalies detected with best threshold: 123
-------------------------------------------------------------------------------------
Anomaly prediction completed.
Number of anomalies detected: 1 with threshold 19121.05303955078, std
Number of anomalies detected: 44 with threshold 105.24900436401367, mad
Number of anomalies detected: 9 with threshold 371.66219024658193, percentile
Number of anomalies detected: 19 with threshold 185.85433959960938, IQR
Number of anomalies detected: 164 with threshold 0.0, zero
choosen threshold type: mad, with value: 105.2490
F1 Score: 0.8354
Accuracy: 0.9207
Precision: 0.7500
Recall: 0.9429
precision recall f1-score support
0 0.98 0.91 0.95 129
1 0.75 0.94 0.84 35
accuracy 0.92 164
macro avg 0.87 0.93 0.89 164
weighted avg 0.93 0.92 0.92 164
ROC AUC Score: 0.9630
c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\src\models_funtions.py:67: RuntimeWarning: invalid value encountered in divide c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\.venv\Lib\site-packages\numpy\lib\type_check.py:518: RuntimeWarning: overflow encountered in cast c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\.venv\Lib\site-packages\numpy\lib\type_check.py:519: RuntimeWarning: overflow encountered in cast
Anomalies detected: 44
Best threshold: 99.6220 | F1 Score: 0.8642 | Precision: 0.7609 | Recall: 1.0000
Anomalies detected with best threshold: 46
-------------------------------------------------------------------------------------
Anomaly prediction completed.
Number of anomalies detected: 2 with threshold 29960.27783203125, std
Number of anomalies detected: 12 with threshold 495.915771484375, mad
Number of anomalies detected: 8 with threshold 574.9293212890625, percentile
Number of anomalies detected: 3 with threshold 666.8313217163086, IQR
Number of anomalies detected: 141 with threshold 0.0, zero
choosen threshold type: mad, with value: 495.9158
F1 Score: 0.0294
Accuracy: 0.5319
Precision: 0.0833
Recall: 0.0179
precision recall f1-score support
0 0.57 0.87 0.69 85
1 0.08 0.02 0.03 56
accuracy 0.53 141
macro avg 0.33 0.44 0.36 141
weighted avg 0.38 0.53 0.43 141
ROC AUC Score: 0.8189
c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\src\models_funtions.py:67: RuntimeWarning: invalid value encountered in divide c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\.venv\Lib\site-packages\numpy\lib\type_check.py:518: RuntimeWarning: overflow encountered in cast c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\.venv\Lib\site-packages\numpy\lib\type_check.py:519: RuntimeWarning: overflow encountered in cast
Anomalies detected: 12 Best threshold: 192.0957 | F1 Score: 0.8271 | Precision: 0.7143 | Recall: 0.9821 Anomalies detected with best threshold: 77 -------------------------------------------------------------------------------------
c:\Users\VG User\Documents\GitHub\MLinAPP-FP01-14\src\models_funtions.py:67: RuntimeWarning: invalid value encountered in divide
In [ ]:
plot_anomalies_true_and_predicted(df_collisions_raw, df_collisions_raw_action, collisions_zones, df_test, title="Collisions zones vs predicted zones for both recordings")
In [ ]:
plot_anomalies_true_and_predicted(df_collisions_raw_1, df_collisions_raw_action_1, collisions_zones_1, df_test_1, title="Collisions zones vs predicted zones for recording 1")
In [ ]:
plot_anomalies_true_and_predicted(df_collisions_raw_5, df_collisions_raw_action_5, collisions_zones_5, df_test_5, title="Collisions zones vs predicted zones for recording 5")